In a method for document analysis, receiving a request to translate a document, identifying usage information corresponding to the document, wherein the usage information includes information corresponding to a current viewing session of the document and historical usage information corresponding to one or more previous viewing sessions of the document, and determining one or more sections of the document to translate based on the identified usage information corresponding to the document.
Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method for document analysis, the method comprising: receiving, by one or more processors, a request to translate a document; determining, by one or more processors, usage information corresponding to the document, wherein the usage information includes information corresponding to a current viewing session of the document for a user, and a mode of usage corresponding to the current viewing session of the document, the mode of usage indicating user activity that corresponds to how the user is currently interacting with the document in the current viewing session of the document, and the mode of usage indicating at least a speed at which the user is scrolling through the document, and wherein the usage information includes historical usage information corresponding to one or more previous viewing sessions of the document; and determining, by one or more processors, one or more sections of the document to translate based on the determined usage information corresponding to the document, wherein the determining one or more sections of the document to translate based on the determined usage information corresponding to the document, further comprises: determining, by one or more processors, a probability corresponding to each section of the one or more sections of the document that indicate the probability that a user will access and view a respective section of the document, wherein the probabilities are determined based on at least: the determined usage information corresponding to the document, data indicating relationships of sections of the document, and browsing history of the document; and determining, by one or more processors, the one or more sections of the document to translate, wherein the one or more sections of the document to translate each have a determined corresponding probability exceeding a minimum threshold condition.
A document analysis method translates parts of a document based on how the user interacts with it. When a translation request arrives, the system analyzes "usage information." This includes current session data like how fast the user scrolls and previous session data. The system calculates the probability each section will be accessed by the user, considering the usage information, the relationships between sections, and the document's browsing history. Only sections with a probability above a defined threshold are selected for translation.
2. The method of claim 1 , wherein determining one or more sections of the document to translate based on the determined usage information corresponding to the document, further comprises: identifying, by one or more processors, a section of the document that is being accessed at the time the request to translate the document is received; translating, by one or more processors, the identified section of the document; determining, by one or more processors, one or more additional sections of the document to translate based on the determined usage information corresponding to the document; and translating, by one or more processors, the determined one or more additional sections of the document.
Building upon the document analysis method of the previous description, when a translation request is received, the section of the document the user is currently viewing is immediately translated. Then, additional sections are chosen for translation based on usage information, historical data, and probabilities of access. These additional sections are then also translated. So, the currently viewed section is always translated, and other sections are translated based on predictive usage.
3. The method of claim 1 , wherein the information corresponding to a current viewing session of the document includes patterns of usage corresponding to the current session.
In the document analysis method described previously, the "information corresponding to a current viewing session" used to determine what to translate includes usage patterns observed during the current session. This refers to how the user is currently interacting with the document, such as scrolling patterns, mouse movements, or time spent on each section. These patterns are considered when deciding which sections to translate.
4. The method of claim 1 , wherein the historical usage information corresponding to previous viewing sessions of the document includes previous usage information associated with a current user of the document and statistical information indicating previous navigation paths through sections of the document taken by previous users of the document.
Regarding the document analysis method from before, the "historical usage information corresponding to previous viewing sessions" used to decide what to translate consists of two parts: previous usage data of the current user, plus statistical data showing navigation paths taken by other users. Therefore, the system translates sections not just based on current behavior, but also on the user's past behavior and the collective behavior of other users.
5. The method of claim 1 , further comprising: translating, by one or more processors, the determined one or more sections of the document.
The document analysis method described previously includes the step of translating the sections of the document that were determined to be the most relevant based on usage data and access probabilities.
6. The method of claim 1 , further comprising: identifying, by one or more processors, previously translated instances of at least one of the one or more determined sections of the document; and providing, by one or more processors, the identified previously translated instances of at least one of the one or more determined sections of the document.
In the document analysis method from before, the system checks if the sections it has chosen to translate have already been translated previously. If previously translated versions exist, the system provides these pre-existing translations instead of generating new translations. This reuses prior work.
7. A computer program product for document analysis, the computer program product comprising: one or more computer readable storage media and program instructions stored on the one or more computer readable storage media, the program instructions comprising: program instructions to receive a request to translate a document; program instructions to determine usage information corresponding to the document, wherein the usage information includes information corresponding to a current viewing session of the document for a user, and a mode of usage corresponding to the current viewing session of the document, the mode of usage indicating user activity that corresponds to how the user is currently interacting with the document in the current viewing session of the document, and the mode of usage indicating at least a speed at which the user is scrolling through the document, and wherein the usage information includes historical usage information corresponding to one or more previous viewing sessions of the document; and program instructions to determine one or more sections of the document to translate based on the determined usage information corresponding to the document, wherein the program instructions to determine one or more sections of the document to translate based on the determined usage information corresponding to the document, further comprise program instructions to: determine a probability corresponding to each section of the one or more sections of the document that indicate the probability that a user will access and view a respective section of the document, wherein the probabilities are determined based on at least: the determined usage information corresponding to the document, data indicating relationships of sections of the document, and browsing history of the document; and determine the one or more sections of the document to translate, wherein the one or more sections of the document to translate each have a determined corresponding probability exceeding a minimum threshold condition.
This describes a computer program to translate documents based on user behavior. The program receives a translation request and determines document "usage information." This includes the user's current session data (like scrolling speed) and historical session data. The program calculates the likelihood a user will access and view specific sections, based on usage data, relationships between sections, and browsing history. Only sections exceeding a probability threshold are translated.
8. The computer program product of claim 7 , wherein the program instructions to determine one or more sections of the document to translate based on the determined usage information corresponding to the document, further comprise program instructions, stored on the one or more computer readable storage media, to: identify a section of the document that is being accessed at the time the request to translate the document is received; translate the identified section of the document; determine one or more additional sections of the document to translate based on the determined usage information corresponding to the document; and translate the determined one or more additional sections of the document.
Expanding on the computer program translation description from earlier, the program translates the section of the document that the user is currently viewing as soon as the translation request is received. Then, it determines additional sections to translate based on usage patterns, historical data and access probability calculations. These additional sections are then translated, providing both immediate translation of the viewed section and predictive translation of other relevant sections.
9. The computer program product of claim 7 , wherein the information corresponding to a current viewing session of the document includes patterns of usage corresponding to the current session.
Referring to the computer program from a previous description, the "information corresponding to a current viewing session" includes usage patterns observed during the current session such as scrolling behavior, cursor movements, and time spent on different sections.
10. The computer program product of claim 7 , wherein the historical usage information corresponding to previous viewing sessions of the document includes previous usage information associated with a current user of the document and statistical information indicating previous navigation paths through sections of the document taken by previous users of the document.
Regarding the computer program translation of documents from before, the "historical usage information" includes both the current user's previous document interactions, and statistical summaries of how previous users navigated the document. The statistical data includes popular navigation paths taken by other users.
11. The computer program product of claim 7 , further comprising program instructions, stored on the one or more computer readable storage media, to: translate the determined one or more sections of the document.
The computer program from before translates the document sections identified as relevant, based on usage analysis and access probabilities.
12. The computer program product of claim 7 , further comprising program instructions, stored on the one or more computer readable storage media, to: identify previously translated instances of at least one of the one or more determined sections of the document; and provide the identified previously translated instances of at least one of the one or more determined sections of the document.
Expanding on the computer program from earlier, the program searches for any previously translated versions of the identified sections. If previously translated versions exist, the program provides the existing translations.
13. A computer system for document analysis, the computer system comprising: one or more computer processors; one or more computer readable storage media; and program instructions stored on the computer readable storage media for execution by at least one of the one or more processors, the program instructions comprising: program instructions to receive a request to translate a document; program instructions to determine usage information corresponding to the document, wherein the usage information includes information corresponding to a current viewing session of the document for a user, and a mode of usage corresponding to the current viewing session of the document, the mode of usage indicating user activity that corresponds to how the user is currently interacting with the document in the current viewing session of the document, and the mode of usage indicating at least a speed at which the user is scrolling through the document, and wherein the usage information includes historical usage information corresponding to one or more previous viewing sessions of the document; and program instructions to determine one or more sections of the document to translate based on the determined usage information corresponding to the document, wherein the program instructions to determine one or more sections of the document to translate based on the determined usage information corresponding to the document, further comprise program instructions to: determine a probability corresponding to each section of the one or more sections of the document that indicate the probability that a user will access and view a respective section of the document, wherein the probabilities are determined based on at least: the determined usage information corresponding to the document, data indicating relationships of sections of the document, and browsing history of the document; and determine the one or more sections of the document to translate, wherein the one or more sections of the document to translate each have a determined corresponding probability exceeding a minimum threshold condition.
A computer system translates documents based on user interaction. It receives a translation request and determines document usage information. This includes the user's current session information (like scrolling speed) and historical data. The system calculates access probabilities for each section based on usage, section relationships, and browsing history. Sections exceeding a probability threshold are selected for translation.
14. The computer system of claim 13 , wherein the program instructions to determine one or more sections of the document to translate based on the determined usage information corresponding to the document, further comprise program instructions, stored on the computer readable storage media for execution by at least one of the one or more processors, to: identify a section of the document that is being accessed at the time the request to translate the document is received; translate the identified section of the document; determine one or more additional sections of the document to translate based on the determined usage information corresponding to the document; and translate the determined one or more additional sections of the document.
Building upon the computer system translation description from earlier, when a translation request comes in, the section of the document currently being viewed is translated immediately. Afterwards, other document sections are selected for translation, based on both usage information and calculated access probability. These additional sections are then translated. So the system handles current request and predicts future needs.
15. The computer system of claim 13 , wherein the information corresponding to a current viewing session of the document includes patterns of usage corresponding to the current session.
Regarding the computer system from before, the "information corresponding to a current viewing session" includes observed usage patterns such as scrolling behaviors, cursor movements, and time spent viewing sections.
16. The computer system of claim 13 , wherein the historical usage information corresponding to previous viewing sessions of the document includes previous usage information associated with a current user of the document and statistical information indicating previous navigation paths through sections of the document taken by previous users of the document.
In the computer system for document translation from earlier, the "historical usage information" consists of the current user's previous document interactions, along with statistical data showing how past users navigated the document, including common navigation paths.
17. The computer system of claim 13 , further comprising program instructions, stored on the computer readable storage media for execution by at least one of the one or more processors, to: translate the determined one or more sections of the document.
The computer system described previously translates the document sections identified as relevant using analysis of user behavior.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
May 23, 2014
June 27, 2017
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.